[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DE5FVTQD8RAG13ZJVHVRCX":3,"skill-same:01M6DE5FVTQD8RAG13ZJVHVRCX":93},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":14,"repositoryHtmlUrl":52,"repositoryHomepageUrl":6,"ownerHtmlUrl":53,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":54,"install":55,"resources":68},"01M6DE5FVTQD8RAG13ZJVHVRCX","diff-blind-test-synth",null,"Use when you want an INDEPENDENT external check that a patch\u002FPR actually satisfies the spec - synthesize executable tests from ONLY the spec + public API (never the diff), then run them against the pre-patch tree (expect FAIL) and the patched tree (expect PASS). A divergence flags a spec-miss or over\u002Funder-fitted patch. Distinct from fail-first\u002Fred-proof. SHADOW mode: never blocks.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-blind-test-synth\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"test","diff blind test synth","diff","red","spec","tests","synthesize","flags","Shadow","shadow mode","patch","only","never","use","check","public","api","first","run","pr","2026-11-10 10:12:30",false,"---\nname: diff-blind-test-synth\ndescription: \"Use when you want an INDEPENDENT external check that a patch\u002FPR actually satisfies the spec - synthesize executable tests from ONLY the spec + public API (never the diff), then run them against the pre-patch tree (expect FAIL) and the patched tree (expect PASS). A divergence flags a spec-miss or over\u002Funder-fitted patch. Distinct from fail-first\u002Fred-proof. SHADOW mode: never blocks.\"\n---\n# Diff-Blind Adversarial Test Synthesis\n\nThe fixing agent authored the patch AND (usually) the tests that prove it — so \"tests pass\" only proves the patch is self-consistent, not that it meets the requirement. The one signal the author cannot fabricate is a test written by someone who **never saw the diff**. This skill produces that signal: a fresh Opus, given only the spec and the public API surface, writes executable tests; their PASS\u002FFAIL pattern across the pre-patch and post-patch trees is an external oracle on whether the patch does what the spec asked.\n\nGrounded in UTBoost (arXiv 2506.09289): LLM-synthesized, ground-truth-blind tests materially raise the bug-detection power of a patch benchmark by catching patches that pass the shipped suite yet miss the actual fix.\n\n## When to run\n- Reviewing a fleet\u002FCodex\u002Fsubagent patch or PR where the author wrote both code and tests.\n- A bugfix task where you want proof the fix addresses the REQUIREMENT, not just the author's chosen test.\n- Before adopting a \"green-tested\" change you did not write, when the spec is concrete enough to author tests from.\n- NOT for: pure refactors with no behavioral spec; changes whose spec is only visible in the diff itself.\n\n## What makes this distinct (do not conflate)\n- **vs A3 fail-first \u002F red-proof gate:** that gate takes the AUTHOR's changed tests and proves they fail on the merge-base. Here the tests are authored **blind to the diff** by a fresh context — it catches the case where the author's own tests are tautological or under-specify the requirement.\n- **vs A4 \u002F execution-consensus best-of-N rerank:** that picks the best among several candidate patches by behavioral clustering. Here there is ONE patch and the oracle is spec-derived tests, not candidate agreement.\n- The three compose: red-proof validates the author's tests, diff-blind adds independent tests, consensus ranks candidates.\n\n## Diff-blindness is the whole point — enforce the isolation\nThe synthesizing agent must receive the spec + public API\u002Fsignatures ONLY. It must NEVER receive: the diff, the patched file bodies, the author's new tests, the PR description's implementation notes, or your own summary of the fix. Any leak makes the test co-author the patch and destroys the signal. Hand it a typed, minimal context (see step 2) — nothing more.\n\n## Protocol\n1. **Freeze the two trees.** Identify the merge-base (`git merge-base HEAD \u003Cbase>`) = PRE tree, and the patched HEAD = POST tree. Prepare disjoint worktrees so the synthesized tests can run against each without cross-contamination (ride the existing WorktreeCreate flow; do not edit either tree).\n2. **Spawn the diff-blind author (fresh context).** Use the `Agent` tool (general-purpose, Opus) with a prompt containing ONLY:\n   - the requirement\u002Fspec (issue text, DoD, acceptance criteria) — verbatim, no implementation hints;\n   - the public API surface the tests will call (function\u002Fclass signatures, CLI flags, HTTP routes, types) — signatures only, NOT bodies;\n   - the test framework + how to run it (`npx jest`, `pytest`), and the instruction to write only *executable, deterministic, black-box* tests that assert the spec's observable behavior.\n   - Explicit ban: \"You will NOT be shown the implementation or the diff. Do not ask for it. Write tests purely from the spec and signatures.\"\n3. **Run the synthesized tests against BOTH trees** (never let the author run them — you run, to keep the author blind):\n   - PRE (merge-base): expect **FAIL** (the requirement was not yet implemented).\n   - POST (patched HEAD): expect **PASS** (the patch implements it).\n4. **Read the pattern** (this is the verdict, logged not enforced):\n\n   | PRE | POST | Verdict | Meaning |\n   |-----|------|---------|---------|\n   | FAIL | PASS | `SPEC_MET` | Patch implements the requirement (external confirmation). |\n   | FAIL | FAIL | `SPEC_MISS` | Patch does NOT satisfy the spec — the strongest catch. Surface the failing case. |\n   | PASS | PASS | `NO_SIGNAL` | Test doesn't exercise the change (already-true, or wrong target). Discard\u002Fregenerate. |\n   | PASS | FAIL | `REGRESSION` | Patch broke behavior the spec required. Surface. |\n   | error | * | `INVALID` | Test didn't compile\u002Fimport against the API — regenerate with corrected signatures. |\n5. **Record + surface.** Write the verdict to the event ledger via `note.py` (e.g. `DIFF_BLIND:SPEC_MET` \u002F `DIFF_BLIND:SPEC_MISS \u003Cfailing test>`). On `SPEC_MISS` \u002F `REGRESSION`, report the concrete failing assertion to the reviewer — do NOT auto-block.\n\n## SHADOW mode (per council C5 — always ship observe-only)\nThis gate NEVER blocks a commit, PR, or task and NEVER nags. It emits a `DIFF_BLIND:\u003Cverdict>` ledger line + a one-line reviewer note, nothing else. Promote OFF→SHADOW→ADVISE→ENFORCE only after a burn-in shows low false-`SPEC_MISS` rate (flaky\u002Fnon-deterministic synthesized tests are the main failure mode — a `SPEC_MISS` that is really test flake). Until then it is advisory signal for a human, never an automated stop.\n\n## Anti-flake \u002F anti-overfit guards\n- Require deterministic tests only; re-run any `SPEC_MISS` once to rule out flake before surfacing (double-fail = real).\n- If POST fails only because the synthesized test asserts an implementation detail the spec never named, that is an over-specified test, not a `SPEC_MISS` — discard it (the spec is the contract, not the patch's internals).\n- Cross-vendor bonus: synthesizing with a DIFFERENT model than authored the patch (e.g. Codex via `mcp__codex__codex`) makes the test's blind spots independent of the patch's — strongest when the patch and the tests come from different models.\n\n## Inline runner (shadow-mode, write on demand — no separate skill file)\nOnce the diff-blind author has produced a test file, run it against both trees and log the verdict. Example for a Python patch (adapt paths \u002F `jest` analogously):\n\n```bash\n# $BASE = merge-base, $TESTFILE = diff-blind synthesized test, $PKG = importable package\nset -u\nrun_tree () {  # $1 = git ref, prints PASS|FAIL|ERROR\n  wt=$(mktemp -d)\n  git worktree add -q --detach \"$wt\" \"$1\" 2>\u002Fdev\u002Fnull || { echo ERROR; return; }\n  cp \"$TESTFILE\" \"$wt\u002Fdiff_blind_test.py\"\n  ( cd \"$wt\" && python -m pytest -q diff_blind_test.py >\u002Fdev\u002Fnull 2>&1 ) \\\n    && echo PASS || { [ $? -eq 1 ] && echo FAIL || echo ERROR; }\n  git worktree remove -f \"$wt\" 2>\u002Fdev\u002Fnull\n}\nPRE=$(run_tree \"$BASE\"); POST=$(run_tree HEAD)\ncase \"$PRE\u002F$POST\" in\n  FAIL\u002FPASS)  V=SPEC_MET ;;\n  FAIL\u002FFAIL)  V=SPEC_MISS ;;\n  PASS\u002FPASS)  V=NO_SIGNAL ;;\n  PASS\u002FFAIL)  V=REGRESSION ;;\n  *)          V=INVALID ;;\nesac\necho \"DIFF_BLIND:$V pre=$PRE post=$POST\"   # SHADOW: log only, exit 0 always\n```\npytest exit codes: 0=all passed, 1=tests failed, ≥2=collection\u002Ferror → maps to PASS\u002FFAIL\u002FERROR above. The runner is observe-only: it always exits 0 and emits the ledger line; it never returns a blocking status.\n","# Diff-Blind Adversarial Test Synthesis\n\nThe fixing agent authored the patch AND (usually) the tests that prove it — so \"tests pass\" only proves the patch is self-consistent, not that it meets the requirement. The one signal the author cannot fabricate is a test written by someone who **never saw the diff**. This skill produces that signal: a fresh Opus, given only the spec and the public API surface, writes executable tests; their PASS\u002FFAIL pattern across the pre-patch and post-patch trees is an external oracle on whether the patch does what the spec asked.\n\nGrounded in UTBoost (arXiv 2506.09289): LLM-synthesized, ground-truth-blind tests materially raise the bug-detection power of a patch benchmark by catching patches that pass the shipped suite yet miss the actual fix.\n\n## When to run\n- Reviewing a fleet\u002FCodex\u002Fsubagent patch or PR where the author wrote both code and tests.\n- A bugfix task where you want proof the fix addresses the REQUIREMENT, not just the author's chosen test.\n- Before adopting a \"green-tested\" change you did not write, when the spec is concrete enough to author tests from.\n- NOT for: pure refactors with no behavioral spec; changes whose spec is only visible in the diff itself.\n\n## What makes this distinct (do not conflate)\n- **vs A3 fail-first \u002F red-proof gate:** that gate takes the AUTHOR's changed tests and proves they fail on the merge-base. Here the tests are authored **blind to the diff** by a fresh context — it catches the case where the author's own tests are tautological or under-specify the requirement.\n- **vs A4 \u002F execution-consensus best-of-N rerank:** that picks the best among several candidate patches by behavioral clustering. Here there is ONE patch and the oracle is spec-derived tests, not candidate agreement.\n- The three compose: red-proof validates the author's tests, diff-blind adds independent tests, consensus ranks candidates.\n\n## Diff-blindness is the whole point — enforce the isolation\nThe synthesizing agent must receive the spec + public API\u002Fsignatures ONLY. It must NEVER receive: the diff, the patched file bodies, the author's new tests, the PR description's implementation notes, or your own summary of the fix. Any leak makes the test co-author the patch and destroys the signal. Hand it a typed, minimal context (see step 2) — nothing more.\n\n## Protocol\n1. **Freeze the two trees.** Identify the merge-base (`git merge-base HEAD \u003Cbase>`) = PRE tree, and the patched HEAD = POST tree. Prepare disjoint worktrees so the synthesized tests can run against each without cross-contamination (ride the existing WorktreeCreate flow; do not edit either tree).\n2. **Spawn the diff-blind author (fresh context).** Use the `Agent` tool (general-purpose, Opus) with a prompt containing ONLY:\n   - the requirement\u002Fspec (issue text, DoD, acceptance criteria) — verbatim, no implementation hints;\n   - the public API surface the tests will call (function\u002Fclass signatures, CLI flags, HTTP routes, types) — signatures only, NOT bodies;\n   - the test framework + how to run it (`npx jest`, `pytest`), and the instruction to write only *executable, deterministic, black-box* tests that assert the spec's observable behavior.\n   - Explicit ban: \"You will NOT be shown the implementation or the diff. Do not ask for it. Write tests purely from the spec and signatures.\"\n3. **Run the synthesized tests against BOTH trees** (never let the author run them — you run, to keep the author blind):\n   - PRE (merge-base): expect **FAIL** (the requirement was not yet implemented).\n   - POST (patched HEAD): expect **PASS** (the patch implements it).\n4. **Read the pattern** (this is the verdict, logged not enforced):\n\n   | PRE | POST | Verdict | Meaning |\n   |-----|------|---------|---------|\n   | FAIL | PASS | `SPEC_MET` | Patch implements the requirement (external confirmation). |\n   | FAIL | FAIL | `SPEC_MISS` | Patch does NOT satisfy the spec — the strongest catch. Surface the failing case. |\n   | PASS | PASS | `NO_SIGNAL` | Test doesn't exercise the change (already-true, or wrong target). Discard\u002Fregenerate. |\n   | PASS | FAIL | `REGRESSION` | Patch broke behavior the spec required. Surface. |\n   | error | * | `INVALID` | Test didn't compile\u002Fimport against the API — regenerate with corrected signatures. |\n5. **Record + surface.** Write the verdict to the event ledger via `note.py` (e.g. `DIFF_BLIND:SPEC_MET` \u002F `DIFF_BLIND:SPEC_MISS \u003Cfailing test>`). On `SPEC_MISS` \u002F `REGRESSION`, report the concrete failing assertion to the reviewer — do NOT auto-block.\n\n## SHADOW mode (per council C5 — always ship observe-only)\nThis gate NEVER blocks a commit, PR, or task and NEVER nags. It emits a `DIFF_BLIND:\u003Cverdict>` ledger line + a one-line reviewer note, nothing else. Promote OFF→SHADOW→ADVISE→ENFORCE only after a burn-in shows low false-`SPEC_MISS` rate (flaky\u002Fnon-deterministic synthesized tests are the main failure mode — a `SPEC_MISS` that is really test flake). Until then it is advisory signal for a human, never an automated stop.\n\n## Anti-flake \u002F anti-overfit guards\n- Require deterministic tests only; re-run any `SPEC_MISS` once to rule out flake before surfacing (double-fail = real).\n- If POST fails only because the synthesized test asserts an implementation detail the spec never named, that is an over-specified test, not a `SPEC_MISS` — discard it (the spec is the contract, not the patch's internals).\n- Cross-vendor bonus: synthesizing with a DIFFERENT model than authored the patch (e.g. Codex via `mcp__codex__codex`) makes the test's blind spots independent of the patch's — strongest when the patch and the tests come from different models.\n\n## Inline runner (shadow-mode, write on demand — no separate skill file)\nOnce the diff-blind author has produced a test file, run it against both trees and log the verdict. Example for a Python patch (adapt paths \u002F `jest` analogously):\n\n```bash\n# $BASE = merge-base, $TESTFILE = diff-blind synthesized test, $PKG = importable package\nset -u\nrun_tree () {  # $1 = git ref, prints PASS|FAIL|ERROR\n  wt=$(mktemp -d)\n  git worktree add -q --detach \"$wt\" \"$1\" 2>\u002Fdev\u002Fnull || { echo ERROR; return; }\n  cp \"$TESTFILE\" \"$wt\u002Fdiff_blind_test.py\"\n  ( cd \"$wt\" && python -m pytest -q diff_blind_test.py >\u002Fdev\u002Fnull 2>&1 ) \\\n    && echo PASS || { [ $? -eq 1 ] && echo FAIL || echo ERROR; }\n  git worktree remove -f \"$wt\" 2>\u002Fdev\u002Fnull\n}\nPRE=$(run_tree \"$BASE\"); POST=$(run_tree HEAD)\ncase \"$PRE\u002F$POST\" in\n  FAIL\u002FPASS)  V=SPEC_MET ;;\n  FAIL\u002FFAIL)  V=SPEC_MISS ;;\n  PASS\u002FPASS)  V=NO_SIGNAL ;;\n  PASS\u002FFAIL)  V=REGRESSION ;;\n  *)          V=INVALID ;;\nesac\necho \"DIFF_BLIND:$V pre=$PRE post=$POST\"   # SHADOW: log only, exit 0 always\n```\npytest exit codes: 0=all passed, 1=tests failed, ≥2=collection\u002Ferror → maps to PASS\u002FFAIL\u002FERROR above. The runner is observe-only: it always exits 0 and emits the ledger line; it never returns a blocking status.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5","skills\u002Fdiff-blind-test-synth","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth",{"tool":61,"command":62},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth",{"tool":64,"command":65},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill diff-blind-test-synth","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Fskills\u002Fdiff-blind-test-synth\u002FSKILL.md",true,[69,75,79,85,89],{"path":70,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":73,"sourceHtmlUrl":74},"assets\u002Fmodule-help.csv","ASSET","资产文件",2890,"https:\u002F\u002Fgithub.com\u002Fdanielmtt9\u002Fbloomcornerkiddies\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-bmb-setup\u002Fassets\u002Fmodule-help.csv",{"path":76,"resourceType":71,"resourceTypeDesc":72,"sizeBytes":77,"sourceHtmlUrl":78},"assets\u002Fmodule.yaml",886,"https:\u002F\u002Fgithub.com\u002Fdanielmtt9\u002Fbloomcornerkiddies\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-bmb-setup\u002Fassets\u002Fmodule.yaml",{"path":80,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fcleanup-legacy.py","SCRIPT","脚本",7743,"https:\u002F\u002Fgithub.com\u002Fdanielmtt9\u002Fbloomcornerkiddies\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-bmb-setup\u002Fscripts\u002Fcleanup-legacy.py",{"path":86,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":87,"sourceHtmlUrl":88},"scripts\u002Fmerge-config.py",14139,"https:\u002F\u002Fgithub.com\u002Fdanielmtt9\u002Fbloomcornerkiddies\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-bmb-setup\u002Fscripts\u002Fmerge-config.py",{"path":90,"resourceType":81,"resourceTypeDesc":82,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fmerge-help-csv.py",6607,"https:\u002F\u002Fgithub.com\u002Fdanielmtt9\u002Fbloomcornerkiddies\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbmad-bmb-setup\u002Fscripts\u002Fmerge-help-csv.py",[94,115,144,168,182,198],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":44},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[101,102,103,104,105,106,107,108,109,37,110,111,112,113,114],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":124,"publishedAt":44},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[121],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[125,126,127,128,129,130,131,132,133,134,135,136,137,138,37,139,140,141,142,143],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":145,"name":146,"nameZh":6,"description":147,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":148,"categories":149,"keywords":154,"publishedAt":44},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[150,153],{"categoryNo":151,"categoryName":152,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[155,156,157,158,159,160,161,162,38,163,126,164,165,166,167],"review","visual","visual review","pages","web","false","iteration","take","slides","ui","screenshot","playwright","screenshots",{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":172,"categories":173,"keywords":174,"publishedAt":44},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[170,175,176,177,178,179,180,181],"setup","report","project","installation","project setup","issues","state",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":189,"publishedAt":44},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[188],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},[184,190,106,191,192,193,37,194,195,196,197],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":199,"name":175,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":203,"publishedAt":44},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[175,177,141,204,179,205],"files","interactive"]